Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Wang, Zhiruo"'
Language models (LMs) are powerful yet mostly for text generation tasks. Tools have substantially enhanced their performance for tasks that require complex skills. However, many works adopt the term "tool" in different ways, raising the question: Wha
Externí odkaz:
http://arxiv.org/abs/2403.15452
Retrieval-augmented generation (RAG) can significantly improve the performance of language models (LMs) by providing additional context for tasks such as document-based question answering (DBQA). However, the effectiveness of RAG is highly dependent
Externí odkaz:
http://arxiv.org/abs/2403.09040
Language models (LMs) can solve tasks such as answering questions about tables or images by writing programs. However, using primitive functions often leads to verbose and error-prone programs, and higher-level functions require expert design. To ena
Externí odkaz:
http://arxiv.org/abs/2401.12869
On-the-fly retrieval of relevant knowledge has proven an essential element of reliable systems for tasks such as open-domain question answering and fact verification. However, because retrieval systems are not perfect, generation models are required
Externí odkaz:
http://arxiv.org/abs/2311.08377
A persistent challenge to table question answering (TableQA) by generating executable programs has been adapting to varied table structures, typically requiring domain-specific logical forms. In response, this paper introduces a unified TableQA frame
Externí odkaz:
http://arxiv.org/abs/2310.14687
Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates recent developments in reward l
Externí odkaz:
http://arxiv.org/abs/2307.04507
Autor:
Yu, Lijun, Cheng, Yong, Wang, Zhiruo, Kumar, Vivek, Macherey, Wolfgang, Huang, Yanping, Ross, David A., Essa, Irfan, Bisk, Yonatan, Yang, Ming-Hsuan, Murphy, Kevin, Hauptmann, Alexander G., Jiang, Lu
In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos. SPAE converts between raw pixels and interpretabl
Externí odkaz:
http://arxiv.org/abs/2306.17842
Autor:
Li, Raymond, Allal, Loubna Ben, Zi, Yangtian, Muennighoff, Niklas, Kocetkov, Denis, Mou, Chenghao, Marone, Marc, Akiki, Christopher, Li, Jia, Chim, Jenny, Liu, Qian, Zheltonozhskii, Evgenii, Zhuo, Terry Yue, Wang, Thomas, Dehaene, Olivier, Davaadorj, Mishig, Lamy-Poirier, Joel, Monteiro, João, Shliazhko, Oleh, Gontier, Nicolas, Meade, Nicholas, Zebaze, Armel, Yee, Ming-Ho, Umapathi, Logesh Kumar, Zhu, Jian, Lipkin, Benjamin, Oblokulov, Muhtasham, Wang, Zhiruo, Murthy, Rudra, Stillerman, Jason, Patel, Siva Sankalp, Abulkhanov, Dmitry, Zocca, Marco, Dey, Manan, Zhang, Zhihan, Fahmy, Nour, Bhattacharyya, Urvashi, Yu, Wenhao, Singh, Swayam, Luccioni, Sasha, Villegas, Paulo, Kunakov, Maxim, Zhdanov, Fedor, Romero, Manuel, Lee, Tony, Timor, Nadav, Ding, Jennifer, Schlesinger, Claire, Schoelkopf, Hailey, Ebert, Jan, Dao, Tri, Mishra, Mayank, Gu, Alex, Robinson, Jennifer, Anderson, Carolyn Jane, Dolan-Gavitt, Brendan, Contractor, Danish, Reddy, Siva, Fried, Daniel, Bahdanau, Dzmitry, Jernite, Yacine, Ferrandis, Carlos Muñoz, Hughes, Sean, Wolf, Thomas, Guha, Arjun, von Werra, Leandro, de Vries, Harm
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15.5B parameter models with 8K context length, infilling capabilitie
Externí odkaz:
http://arxiv.org/abs/2305.06161
To extend the scope of coding queries to more realistic settings, we propose ODEX, the first Open-Domain EXecution-based natural language (NL) to Python code generation dataset. ODEX has 945 NL-Code pairs spanning 79 diverse libraries, along with 1,7
Externí odkaz:
http://arxiv.org/abs/2212.10481
Autor:
Jiang, Zhengbao, Gao, Luyu, Araki, Jun, Ding, Haibo, Wang, Zhiruo, Callan, Jamie, Neubig, Graham
Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers. Retriev
Externí odkaz:
http://arxiv.org/abs/2212.02027